Trust and Transparency in Recommender Systems
Preprint
Abstract
Trust is long recognized to be an important factor in Recommender Systems (RS). However, there are different perspectives on trust and different ways to evaluate it. Moreover, a link between trust and transparency is often assumed but not always further investigated. In this paper we first go through different understandings and measurements of trust in the AI and RS community, such as demonstrated and perceived trust. We then review the relationsships between trust and transparency, as well as mental models, and investigate different strategies to achieve transparency in RS such as explanation, exploration and exploranation (i.e., a combination of exploration and explanation). We identify a need for further studies to explore these concepts as well as the relationships between them.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- The effects of controllability and explainability in a social recommender systemUser Modeling and User-Adapted Interaction, 2020
- Making deep neural networks right for the right scientific reasons by interacting with their explanationsNature Machine Intelligence, 2020
- A systematic review and taxonomy of explanations in decision support and recommender systemsUser Modeling and User-Adapted Interaction, 2017
- Four reference models for transparency requirements in information systemsRequirements Engineering, 2017
- Interactive recommender systems: A survey of the state of the art and future research challenges and opportunitiesExpert Systems with Applications, 2016
- Explaining Recommendations: Design and Evaluation2015
- Evaluating recommender systems from the user’s perspective: survey of the state of the artUser Modeling and User-Adapted Interaction, 2012
- The effects of transparency on trust in and acceptance of a content-based art recommenderUser Modeling and User-Adapted Interaction, 2008
- Visual Analytics: Definition, Process, and Challenges2008
- The dynamics of trust: Comparing humans to automation.Journal of Experimental Psychology: Applied, 2000